Computer Vision at University of Virginia

Course Description

The ability to perceive the visual 3D world is critically important for humans and has extensive applications in robotics, graphics, virtual/augmented reality, and more. This course will delve into the foundational concepts and recent advancements at the intersection of machine learning and computer vision. In particular, we will cover the following topics in this course:

Fundamentals of computer vision: image formation, camera models
Machine learning basics: datasets, objective function, optimizer, neural network architectures
Low-level vision: edge detection, image filtering, signal processing
Mid-level vision: depth and surface normal estimation, optical flow, image matching
3D vision: classical multiview geometry, 3D representations
High-level recognition: image classification, object detection, semantic segmentation, 3D recognition
Generative modeling: generative adversarial networks, diffusion models, image/video/3D generation
Biological vision: human and animal visual development
Applications of computer vision: computer cision meets robotics, language, and science

Course Objective

Upon the completion of this course, the students should:

understand the fundamental concepts in computer vision and machine learning;
be equipped with math and machine learning tools to solve computer vision problems
have a big picture of the history and recent trends in computer vision;
learn how to communicate and collaborate in computer vision projects, and how to present efficiently;